This ComfyUI workflow lets you edit a short video by simply describing the change you want. LoadVideo ingests your clip (the template includes input/hooded_wanderer_planet_bridge.mp4 as a ready-to-run test), and GeminiVideoOmniV2 sends both the video and your plain‑language instruction to Gemini Omni 1.1 Flash. The model applies targeted edits—like swapping backgrounds, restyling a scene, or adding/removing elements—while leaving everything else untouched. For maximum fidelity, include a line such as “Keep everything else the same.” Simple, direct prompts tend to produce the most consistent results.
On output, SaveVideo writes the edited clip to disk with the native audio preserved. You can choose 16:9 or 9:16 and render at 1080p or 4K, making it suitable for landscape or vertical content. A MarkdownNote in the graph provides quick tips. The recommended input duration is 10 seconds or less to ensure responsive processing and stable edits. This setup is ideal for rapid remixes and iterative refinement without regenerating entire scenes from scratch.
API
從程式碼使用此工作流
每個 Comfy 工作流都是一個 JSON 圖。下方的 payload 就是此工作流，與 ComfyUI 執行時完全相同 — 你可以從此 URL 取得、放入版本控制，或在 ComfyUI 載入並逐節點執行。
使用 Comfy SDK 以 TypeScript 或 Python 執行。相同程式碼可用於 Comfy Cloud 或你自架的 ComfyUI — 只需更改 base URL。
// Install (beta)
npm i @comfyorg/sdk
// Run this workflow (TypeScript)
import { Comfy } from "@comfyorg/sdk";
const client = new Comfy({ apiKey: "comfyui-..." });
const wf = await client.workflows.fromFile("workflow_api.json");
const job = await client.run(wf);
await job.getOutputs("<output-node-id>")[0].toFile("output.png");SDK 需使用 API 格式的工作流：請在 ComfyUI 開啟此工作流，並使用 檔案 → 匯出工作流（API）。
